PocketSphinx语音识别系统----声学模型的训练与使用

最新推荐文章于 2020-04-30 11:07:01 发布

皮熊

最新推荐文章于 2020-04-30 11:07:01 发布

阅读量1.2k

点赞数

CC 4.0 BY-SA版权

分类专栏：语音识别与语音合成

本文链接：https://blog.youkuaiyun.com/ppp2006/article/details/22156695

本文介绍了使用PocketSphinx创建新语言数据库的步骤，包括手动或自动收集音频，设计数据库结构，准备数据文件，录制语音指令，并详细说明了训练和测试声学模型的过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

The good ways to obtain a database for a new language are:

Manually segment audio recordings with existing transcription (podcasts, news, etc)
Record your friends and family and colleagues
Setup automated collection on Voxforge

You have to design database prompts and postprocess the results to ensure that audio actually correspondsto prompts. The file structure for the database is:

etc
- your_db.dic - Phonetic dictionary
- your_db.phone - Phoneset file
- your_db.lm.DMP - Language model
- your_db.filler - List of fillers
- your_db_train.fileids - List of files for training
- your_db_train.transcription - Transcription for training
- your_db_test.fileids - List of files for testing
- your_db_test.transcription - Transcription for testing
wav
- speaker_1
  - file_1.wav - Recording of speech utterance
- speaker_2
  - file_2.wav